diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-09-16 16:47:36 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-09-16 16:47:36 +0300 |
| commit | 2874b984006c6c8d0691ce000dcd9ca2cf9ff6fd (patch) | |
| tree | 4244cf6b022a6eb728f5d0eb3ba94a739681e345 /examples/server/tests/tests.sh | |
| parent | 20f3e6fd2de6378d2a598b48edce369642bf2ee8 (diff) | |
iqk_mul_mat(ARM_NEON): adding bf16 support (#41)
It looks like ArmV8 ISA has support for bf16, but my M2 Max
does not have it, so resorting to bf16 -> f32 conversion and
computations in f32. This is 2x slower than f16, but 8x better
compared to what I get if I try to run a bf16 model on the M2
(NEON and Metal).
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/server/tests/tests.sh')
0 files changed, 0 insertions, 0 deletions